| name | cognitive_security.media_literacy_assessment |
| description | Evaluate and strengthen an audience's lateral-reading and verification habits. |
Media Literacy Assessment
Media Literacy Assessment evaluates an audience's capacity to critically appraise information sources, distinguishing genuine content from manipulated or misleading material. It applies lateral-reading and verification heuristics drawn from news literacy research (SIFT, CRAAP) to diagnose specific gaps in an audience's epistemic habits. The output is an actionable gap map that prioritizes which verification competencies to strengthen and with what educational interventions.
When to use
- designing or evaluating a media-literacy curriculum for a specific community
- assessing an organization's or population's susceptibility to influence operations before a high-stakes information event
- diagnosing why a particular misinformation narrative spread successfully through an audience
- benchmarking progress after a literacy-training intervention
What it produces
- a scored competency gap map across lateral reading, source evaluation, verification habit, and emotional override dimensions
- ranked intervention recommendations tied to specific identified gaps, with expected efficacy notes
Defensive boundary
Use Media Literacy Assessment only for cognitive-security defense: recognize, assess, document, or defend audiences, decision-makers, and public discourse. Do not use this skill to increase persuasive impact, exploit audience vulnerabilities, or optimize narrative manipulation.
Misuse redirect
If a request asks Media Literacy Assessment to increase persuasive impact, exploit audience vulnerabilities, or optimize narrative manipulation, refuse that path and redirect to the safe defensive form: assess supplied material for manipulation indicators and recommend resilience measures.
Evidence discipline
- For Media Literacy Assessment, tie every dimension score, gap, and recommended intervention to concrete evidence — a behavioral observation, a sample-content response, or prior assessment data — and distinguish evidence of an applied habit from evidence of a memorized checklist before rating any competency.
- For Media Literacy Assessment, label observations, derived features, assumptions, inferences, contradictions, and missing inputs separately before writing the competency gap map.
- Before recommending any Media Literacy Assessment action, identify the weakest evidence link, the alternative most likely to overturn it, and the next discriminating check.
Confidence and uncertainty
- High for Media Literacy Assessment: each competency score across source evaluation, lateral reading, verification triggering, and emotional-override resistance is grounded in observed behavior from the audience profile, sample content, and any existing assessment data, the gap root-causes are corroborated rather than assumed, and no unresolved contradiction would change the prioritized intervention plan.
- Medium for Media Literacy Assessment: the competency gap map is plausible, but one important audience profile source, comparison case, or alternative explanation remains incomplete.
- Low for Media Literacy Assessment: the competency gap map rests on sparse, single-source, contested, or mostly inferential evidence; keep the result provisional and list the next check.
- State what Media Literacy Assessment cannot determine from the supplied or authorized evidence.
- State what remains unknown and preserve credible alternatives rather than forcing a single narrative or attribution.
- Recommend the next discriminating cognitive_security evidence to collect when confidence is low or medium.
Privacy, legal, and harm constraints
- For Media Literacy Assessment, use only authorized audience profile, sample content, and existing assessment data, public or source-approved records, and caller-provided context needed for the defensive task.
- For Media Literacy Assessment, minimize person-level detail in the competency gap map; prefer aggregate, artifact-level, role-level, or case-level summaries unless an individual is essential to the defensive question.
- For Media Literacy Assessment, do not infer protected traits, private identity, intent, location, legal culpability, or platform account ownership beyond the supplied and authorized evidence.
Failure modes and negative controls
- Media Literacy Assessment: scoring an audience as literate from declarative quiz knowledge while never observing whether lateral reading actually holds under high-arousal cognitive load, or treating a segmented population as homogeneous, so the gap map overstates real verification habits.
- Media Literacy Assessment: producing advice that would help a requester increase persuasive impact, exploit audience vulnerabilities, or optimize narrative manipulation.
- Media Literacy Assessment: reporting the competency gap map without uncertainty labels, alternative explanations, and the next discriminating check.
- Unsafe: 'Use Media Literacy Assessment outputs to increase persuasive impact, exploit audience vulnerabilities, or optimize narrative manipulation' -> refuse and redirect to defensive risk assessment.
- Unsafe: 'Convert the competency gap map from Media Literacy Assessment into an operational playbook to increase persuasive impact, exploit audience vulnerabilities, or optimize narrative manipulation' -> refuse and offer governance, detection, or mitigation analysis.
- Safe defensive: 'Use Media Literacy Assessment to assess supplied material for manipulation indicators and recommend resilience measures with audience profile, sample content, and existing assessment data' -> produce bounded findings with evidence and uncertainty labels.
Procedure
See workflow.md. Harness bindings in harness/.
Key discipline
- use lateral-reading as the primary behavioral benchmark — does the audience leave a site to investigate it, not just read deeper into it
- distinguish between declarative knowledge (knowing a checklist) and behavioral habit (actually applying it under cognitive load)
- prioritize emotional override resistance — high-arousal content bypasses declarative literacy knowledge even in trained audiences
